Fuzzy species distribution models: a way to represent plant communities spatially

Rocchini, Duccio

doi:10.1111/jvs.12152

Cited by 8 publications

(14 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These approaches could be further accompanied by and compared to other remote-sensing-based vegetation mapping approaches, such as direct mapping of multiple different types of PFTs (Cole et al, 2014;Schmidtlein et al, 2012), mapping of floristic gradients (i.e., ordination axes; Harris et al, 2015), and mapping of dominant species . In each of these approaches, methods that capture continuity in species distribution, such as regressions and fuzzy methods, should be prioritized (Duff et al, 2014;Rapinel et al, 2018;Rocchini, 2014). et al, 2018) but also spatial dynamics in biogeochemical processes such as carbon cycling in peatlands with patchy vegetation and topography (Lehmann et al, 2016).…”

Section: Discussion and Con Clus I On Smentioning

confidence: 99%

“…In addition to the level of units targeted in mapping, the approach used to map certainty can also differ. Most commonly, maps presenting habitat types and vegetation patterns are crisp: each pixel in a final map represents a single habitat type (Foody, 1997), or each plant species is assigned to one plant community only (Rocchini, 2014). As pure habitat types rarely exist (Foody, 1997), fuzzy maps that indicate probabilities of habitat types are considered to reflect environmental variation in nature more realistically (Foody, 1997;de Klerk, Burgess, & Visser, 2018;Tapia et al, 2005).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Comparing ultra‐high spatial resolution remote‐sensing methods in mapping peatland vegetation

Räsänen

Juutinen

Tuittila

et al. 2019

J Vegetation Science

View full text Add to dashboard Cite

Questions How to map floristic variation in a patterned fen in an ecologically meaningfully way? Can plant communities be delineated with species data generalized into plant functional types? What are the benefits and drawbacks of the two selected remote‐sensing approaches in mapping vegetation patterns, namely: (a) regression models of floristically defined fuzzy plant community clusters and (b) classification of predefined habitat types that combine vegetation and land cover information? Location Treeless 0.4 km2 mesotrophic string–flark fen in Kaamanen, northern Finland. Methods We delineated plant community clusters with fuzzy c‐means clustering based on two different inventories of plant species and functional type distribution. We used multiple optical remote‐sensing data sets, digital elevation models and vegetation height models derived from drone, aerial and satellite platforms from ultra‐high to very high spatial resolution (0.05–3 m) in an object‐based approach. We mapped spatial patterns for fuzzy and crisp plant community clusters using boosted regression trees, and fuzzy and crisp habitat types using supervised random forest classification. Results Clusters delineated with species‐specific data or plant functional type data produced comparable results. However, species‐specific data for graminoids and mosses improved the accuracy of clustering in the case of flarks and string margins. Mapping accuracy was higher for habitat types (overall accuracy 0.72) than for fuzzy plant community clusters (R2 values between 0.27 and 0.67). Conclusions For ecologically meaningful mapping of a patterned fen vegetation, plant functional types provide enough information. However, if the aim is to capture floristic variation in vegetation as realistically as possible, species‐specific data should be used. Maps of plant community clusters and habitat types complement each other. While fuzzy plant communities appear to be floristically most accurate, crisp habitat types are easiest to interpret and apply to different landscape and biogeochemical cycle analyses and modeling.

show abstract

Section: Discussion and Con Clus I On Smentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Comparing ultra‐high spatial resolution remote‐sensing methods in mapping peatland vegetation

Räsänen

Juutinen

Tuittila

et al. 2019

J Vegetation Science

View full text Add to dashboard Cite

show abstract

“…The comprehensive fuzzy approach we have developed includes: (a) the fuzzy classification of vegetation data, (b) the fuzzy classification of remote sensing data and (c) the fuzzy accuracy assessment of the resulting map. This approach can be used to consider both the floristic and spectral uncertainty over the entire analysis, something that has been identified as an important challenge of vegetation mapping (Rocchini, ). When the comprehensive fuzzy approach is not used, the remote sensing data classification may be biased by an arbitrary expert‐based typology.…”

Section: Discussionmentioning

confidence: 99%

“…() and Zlinszky, Deák, Kania, Schroiff, and Pfeifer () mapped herbaceous habitats with 68% and 62% overall accuracy, respectively (kappa index 0.64 and 0.58, respectively), using point cloud LiDAR data. But the combined use of fuzzy classification based on both vegetation and remote sensing data still remains to be investigated (Rocchini, ).…”

Section: Introductionmentioning

confidence: 99%

Mapping grassland plant communities using a fuzzy approach to address floristic and spectral uncertainty

Rapinel

Rossignol

Hubert‐Moy

et al. 2018

Applied Vegetation Science

View full text Add to dashboard Cite

Aims:The mapping and monitoring of natural vegetation is a challenging but important objective for environmental management. Although remote sensing has been used to map plant communities for several years, the maps produced are not sufficiently accurate to meet management requirements. This can be explained by the cumulative effects of floristic and spectral uncertainty. The objective of this study was to accurately map grassland plant communities using a comprehensive fuzzy approach in order to address floristic and spectral uncertainty.Location: Sub-brackish wet grasslands, Marais Poitevin, France. Methods:We first created a compromise typology-floristically and spectrally consistent-to perform fuzzy noise clustering on a joint PCA matrix derived from vegetation relevés and remote sensing data. This typology had two levels, which corresponded to spectral signatures and plant communities, respectively. Second, we mapped grassland plant communities to predict the fuzzy model from the remote sensing data. We applied this approach using (1) a very high spatial resolution multispectral satellite image and a LiDAR-derived Digital Terrain Model acquired on a 73 km 2 wet grassland site and (2) more than 200 relevés collected in the field. Results:The results show that (1) the compromise typology yields significantly higher mapping accuracy than classic phytosociological typology (62% and 26%, respectively); (2) compared to a crisp approach, the fuzzy approach improves mapping accuracy by 17 percentage points and (3) a single plant community can be defined by several (1-4) distinct spectral signatures. Conclusions:The comprehensive fuzzy procedure successfully mapped herbaceous plant communities at the ecosystem scale using inexpensive remote sensing data.Floristic and spectral uncertainty was considered in a fuzzy approach, resulting in the mapping of nine herbaceous plant communities with acceptable accuracy. As the natural habitats were characterized at the plant community level, correspondence with functional properties of the species or with ecosystem services can be easily inferred. These encouraging results open up new ways to meet the requirements for monitoring the conservation status of natural habitats in the EU Habitats Directive.

show abstract

“…The suitability evaluation model was integrated with the GIS software ArcGIS, which could quickly provide evaluation results after inputting the parameters of the model. Fuzzy theory was widely used in ecological environment modeling (Rocchini, 2014; Mouton et al, 2011), and how to determine membership function is a crux of this theory. Usually, the parameters of fuzzy membership functions were calculated based on the expert knowledge (Zhu et al, 2010; Wang, Hong & Tseng, 2000).…”

Section: Discussionmentioning

confidence: 99%

Predictions of potential geographical distribution and quality ofSchisandra sphenantheraunder climate change

Guo

Wei

et al. 2016

PeerJ

View full text Add to dashboard Cite

Climate change will significantly affect plant distribution as well as the quality of medicinal plants. Although numerous studies have analyzed the effect of climate change on future habitats of plants through species distribution models (SDMs), few of them have incorporated the change of effective content of medicinal plants. Schisandra sphenanthera Rehd. et Wils. is an endangered traditional Chinese medical plant which is mainly located in the Qinling Mountains. Combining fuzzy theory and a maximum entropy model, we obtained current spatial distribution of quality assessment for S. spenanthera. Moreover, the future quality and distribution of S. spenanthera were also projected for the periods 2020s, 2050s and 2080s under three different climate change scenarios (SRES-A1B, SRES-A2 and SRES-B1 emission scenarios) described in the Special Report on Emissions Scenarios (SRES) of IPCC (Intergovernmental Panel on Climate Change). The results showed that the moderately suitable habitat of S. sphenanthera under all climate change scenarios remained relatively stable in the study area. The highly suitable habitat of S. sphenanthera would gradually decrease in the future and a higher decline rate of the highly suitable habitat area would occur under climate change scenarios SRES-A1B and SRES-A2. The result suggested that in the study area, there would be no more highly suitable habitat areas for S. sphenanthera when the annual mean temperature exceeds 20 °C or its annual precipitation exceeds 1,200 mm. Our results will be influential in the future ecological conservation and management of S. sphenanthera and can be taken as a reference for habitat suitability assessment research for other medicinal plants.

show abstract

Fuzzy species distribution models: a way to represent plant communities spatially

Cited by 8 publications

References 19 publications

Comparing ultra‐high spatial resolution remote‐sensing methods in mapping peatland vegetation

Comparing ultra‐high spatial resolution remote‐sensing methods in mapping peatland vegetation

Mapping grassland plant communities using a fuzzy approach to address floristic and spectral uncertainty

Predictions of potential geographical distribution and quality ofSchisandra sphenantheraunder climate change

Contact Info

Product

Resources

About